Qwen2.5-Coder-1.5B-Instruct-Pollard

Qwen2.5-Coder-1.5B-Instruct — Pollard

Pollard shrank this model: 3.08 GB (f16) → 0.86 GB — 72% smaller, 3.6× down.

The smallest rung here; larger, higher-fidelity rungs are listed below.

format	this model's size
f16	3.08 GB
Q8_0	~1.63 GB
Q6_K	~1.26 GB
Q4_K_M	~0.89 GB
PollardMix (this repo's IQ4_XS)	0.86 GB

Pollard builds of Qwen/Qwen2.5-Coder-1.5B-Instruct made with Pollard Weights — a ladder of measured-allocation quants (bits placed by per-layer sensitivity, not a uniform crush).

Standard GGUF — runs in stock llama.cpp / ik_llama.cpp, Ollama, LM Studio. Trellis (IQ*_KT) files need ik_llama.cpp; the K-quants run anywhere.

Model details

Which file should I choose?

Every rung is the same weights, sized to a different RAM budget by the measured allocation. Pick the largest one that fits your machine with room for context:

• ~3 GB RAM / VRAM → Q6_K (1.27 GB). max fidelity
• ~3 GB RAM / VRAM → Q5_K_M (1.12 GB). balanced — recommended
• ~3 GB RAM / VRAM → IQ4_XS (0.86 GB). fastest / smallest

Available files

tok/s is hardware-specific; the machine it was measured on is stated in the errata.

Measured notes

Local code completion that fits your box. Built with Pollard Weights — sized to your machine's RAM, not to a bit-width chart. Standard GGUF: runs in any recent llama.cpp (the qwen2 architecture is long-supported) and anything built on it. 70–93 tok/s on an Apple M4, whole model under 1.3 GB.

Download a specific file

pip install -U "huggingface_hub[cli]"
hf download PollardWeights/Qwen2.5-Coder-1.5B-Instruct-Pollard \
  --include "Qwen2.5-Coder-1.5B-Instruct-Pollard-Q5_K_M.gguf" --local-dir ./

How to run

These are standard GGUF and run with llama.cpp:

llama-server -hf PollardWeights/Qwen2.5-Coder-1.5B-Instruct-Pollard:Q5_K_M

or from a local file:

llama-cli    -m Qwen2.5-Coder-1.5B-Instruct-Pollard-Q5_K_M.gguf -ngl 99 -p "Explain why the sky is blue."
llama-server -m Qwen2.5-Coder-1.5B-Instruct-Pollard-Q5_K_M.gguf -ngl 99      # OpenAI-compatible API + web UI at :8080

They also work in anything built on llama.cpp — LM Studio, koboldcpp, Jan, ramalama, Ollama (ollama run hf.co/PollardWeights/Qwen2.5-Coder-1.5B-Instruct-Pollard).

imatrix (calibration)

The importance matrix (Qwen2.5-Coder-1.5B-Instruct-Pollard.imatrix, included) was computed on a mixed-domain corpus so the matrix sees every register the model serves.

ARM / AVX

llama.cpp repacks weights into an interleaved layout at load time for faster inference on ARM and AVX machines — no special file needed, online repacking covers these quants. The old Q4_0_4_4/4_8/8_8 variants are not required.

Errata

• Trellis (IQ*_KT) quants need ik_llama.cpp to build/run; K-quants run in any recent llama.cpp.
• Measured allocation places bits by per-layer sensitivity under a size budget.
• Single machine; replication invited.

Credits & license

• Base model: Qwen/Qwen2.5-Coder-1.5B-Instruct
• Quantization tooling: llama.cpp (ggml-org)
• Method + tooling: Pollard Weights — measure first, no claim before a number.
• License: apache-2.0, inherited from the base model.

Built with Pollard Weights — frontier models, small hardware, no compromise.